- Who it is for
- Teams with a question and uncertain data, before committing to a larger project.
- Deliverable
- A written assessment: whether the question is answerable with the data you have, which methods apply, what a full engagement would cost, and what it would produce.
- You provide
- Access to the data or a description of it, and one hour with the decision owner.
- The decision it enables
- A go or no-go on the larger project, with the scope already written.
Services
Four ways to engage, each ending in something your team can run.
Independent quantitative analysis in three areas, delivered through packaged engagements so the scope, the duration, and what you get are clear before work starts.
Areas of work
Energy infrastructure and load growth
Zonal vulnerability and siting screens, load growth and interconnection queue modeling, price and volatility analysis for PJM and other ISOs. Built for a market in which grid capacity, not capital, decides where compute gets built.
See the PJM grid model →Valuation, risk, and market analysis
Valuation models, risk-adjusted comparison, scenario and sensitivity work, grounded in graduate economics and prior M&A advisory rather than assembled from off-the-shelf indicators.
See TickerScope →Document intelligence for regulated material
Retrieval systems over contracts, filings, tariffs, and procedural documents, designed so every output stays traceable to its source and a reviewer can check the reasoning.
See Blackletter →
Which engagement fits
Two questions, one recommendation.
An honest starting point, not a sales funnel. Most first engagements are the diagnostic, because most questions arrive before the data has been looked at.
Recommended
Scoping diagnostic
2 weeks · Fixed fee, quoted after a 30-minute call
A go or no-go on the larger project, with the scope already written.
Start with this →Engagements
What each one includes.
- Who it is for
- Teams that need a defined question answered with a documented model.
- Deliverable
- A model with its assumptions, validation, and limits stated in writing, plus a results memo your team can paste into an investment or planning document.
- You provide
- Data access, a named counterpart, and a weekly 30-minute review.
- The decision it enables
- A decision backed by a method that can be inspected and re-run.
- Who it is for
- Teams whose model has to be used by people who will not open a notebook.
- Deliverable
- The analysis engagement plus a deployed application: scenario controls, maps or charts as appropriate, an API, documentation, and handover.
- You provide
- Everything in the analysis engagement plus a hosting decision and the end users for two review sessions.
- The decision it enables
- A planning or screening tool the wider team can run without you.
- Who it is for
- In-house analytics teams that want an independent review of method and interpretation.
- Deliverable
- Model and method review, a standing weekly call, written comments on analyses before they reach a committee, and short ad hoc studies.
- You provide
- Access to work in progress and a single point of contact.
- The decision it enables
- Analyses that survive scrutiny the first time they are presented.
Not offered
- Business intelligence dashboards and routine reporting
- Staff augmentation or hourly data engineering
- Personal investment advice of any kind
Method
How every engagement runs.
Step 1
Scope the decision
Start from the decision the analysis has to support and the person who will make it. The question is written down and agreed before any data is touched.
Step 2
Audit the data
Establish what the data can and cannot support. Coverage, granularity, gaps, and the difference between what a field is called and what it measures.
Step 3
Model with more than one method
Each method answers a different objection. A machine learning model, a panel regression, and a causal design agreeing is a stronger claim than one well-fit model.
Step 4
Validate and state the limits
Out-of-sample tests, fixed normalization so scenarios stay comparable, and a plain statement of what the result does not cover.
Step 5
Deliver as software and a written result
A memo for the committee and a deployed application for the team. The reasoning is inspectable rather than trusted.
Questions before scoping
How is pricing set?
The scoping diagnostic is a fixed fee quoted after a 30-minute call. Analysis and build engagements are quoted as a range in the diagnostic report, so the price arrives with the scope it covers. Retained advisory is a monthly fee with a three-month minimum.
What data do you need?
Whatever exists. Part of the diagnostic is establishing what the data can support. Public market data (ISO prices, load, EIA, interconnection queues) is often enough for energy questions; finance work usually needs your internal figures under an NDA.
Who owns the model and the code?
You do. Engagements end with a handover: documented code, the trained model, the data pipeline, and a written result. Nothing stays locked in a tool you cannot run.
Do you work with teams outside the United States?
Yes. Based in Miami, working with US and EU teams remotely, with on-site sessions where they matter.
Is this investment advice?
No. The work is analysis for organizations making planning, siting, and valuation decisions. It is not personal investment advice and not an offer or solicitation of any instrument.
Start with a 30-minute scoping call.
I reply within one business day.